Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    configuration settings related to enabling features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    des
    -0.16
    pez
    -0.15
    Ìĥ
    -0.14
     nhau
    -0.14
    ghi
    -0.14
    ole
    -0.13
    cko
    -0.13
    olean
    -0.13
    ved
    -0.13
    öl
    -0.13
    POSITIVE LOGITS
    lobe
    0.15
    onto
    0.15
    yb
    0.15
    .gg
    0.14
    yms
    0.14
    726
    0.14
    696
    0.14
    otal
    0.14
    Å¡lo
    0.14
    íĥķ
    0.14
    Act Density 0.044%

    No Known Activations